Assuring anomaly-free business process executions is a key challenge for many organizations. Traditional techniques address this challenge using prior knowledge about anomalous cases that is seldom available in real-life. In this work, we propose the usage of word2vec encoding and One-Class Classification algorithms to detect anomalies by relying on normal behavior only. We investigated 6 different types of anomalies over 38 real and synthetics event logs, comparing the predictive performance of Support Vector Machine, One-Class Support Vector Machine, and Local Outlier Factor. Results show that our technique is viable for real-life scenarios, overcoming traditional machine learning for a wide variety of settings where only the normal behavior can be labeled.
Anomaly detection on event logs with a scarcity of labels
Barbon Junior S.;
2020-01-01
Abstract
Assuring anomaly-free business process executions is a key challenge for many organizations. Traditional techniques address this challenge using prior knowledge about anomalous cases that is seldom available in real-life. In this work, we propose the usage of word2vec encoding and One-Class Classification algorithms to detect anomalies by relying on normal behavior only. We investigated 6 different types of anomalies over 38 real and synthetics event logs, comparing the predictive performance of Support Vector Machine, One-Class Support Vector Machine, and Local Outlier Factor. Results show that our technique is viable for real-life scenarios, overcoming traditional machine learning for a wide variety of settings where only the normal behavior can be labeled.File | Dimensione | Formato | |
---|---|---|---|
Anomaly_Detection_on_Event_Logs_with_a_Scarcity_of_Labels.pdf
Accesso chiuso
Tipologia:
Documento in Versione Editoriale
Licenza:
Copyright Editore
Dimensione
14.1 MB
Formato
Adobe PDF
|
14.1 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Anomaly_Detection_on_Event_Logs_with_a_Scarcity_of_Labels-Post_print.pdf
accesso aperto
Tipologia:
Bozza finale post-referaggio (post-print)
Licenza:
Digital Rights Management non definito
Dimensione
16.11 MB
Formato
Adobe PDF
|
16.11 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.